Scribd
Upload
8 views

HASTS 412 Assignment-2

Uploaded by

Tapiwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views

HASTS 412 Assignment-2

Uploaded by

Tapiwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

UNIVERSITY OF ZIMBABWE

Applied in Statistics HASTS 412

Longitudinal Data Analysis: Assignment 2

November 2023
Time : ??? hours

Candidates should attempt all questions. Marks will be allocated as indicated.

A1. In a study to evaluate weight loss programs (prog), 62 male subjects were recruited to
participate and were randomly assigned to maintain their current eating and exercise
habits (Control), or to follow a rigorous program of modified diet and exercise (Exer-
cise). All participants were weighed at baseline (month 0) and then again at months
3, 6, 9, and 12. An analyst considered a different linear average trend in time for each
of the programs. Further, a random intercept was used to account for the correlation
between repeated measurements in time.
(a) Using symbols for fixed effects, random effects, and residual error terms, write
down two expressions (i.e., one for each program) describing the trend of weight
loss in the two programs. Please use clear notation, making sure that all symbols
used are defined. [6]
(b) The analyst fitted the intended model in R and provided the following output
> summary(fitM1)
Linear mixed-effects model fit by maximum likelihood
Data: tmpDat
AIC BIC logLik
2595.618 2618.037 -1291.809

Random effects:
Formula: ~1 | id
(Intercept) Residual
StdDev: 18.09413 12.17425

Fixed effects: weight ~ prog + month + prog * month


Value Std.Error DF t-value p-value
(Intercept) 240.84412 3.522061 246 68.38158 0.0000
progExercise 3.35374 5.240995 60 0.63991 0.5247
month 0.54941 0.221514 246 2.48026 0.0138
progExercise:month -7.98727 0.329624 246 -24.23148 0.0000

Number of Observations: 310


Number of Groups: 62

page 1 of 2
HASTS 412

(i) Based on the output, write two explicit expression for the estimated popula-
tion average trends in each of the programs. [3]
(ii) Make an appropriately labelled sketch of the average trends in the two pro-
grams based on your results in b(i). Comment on your plot. [3]
(iii) Use the output above and any other relevant information to verify that the
data collected is balanced longitudinal data. [2]
(iv) Provide an estimate of the correlation between any two values within a subject
over time. [4]
(c) The analyst claimed that the slopes were actually similar between the two groups,
and provided output for another model that was considered
> summary(fitM2)
Linear mixed-effects model fit by maximum likelihood
Data: tmpDat
AIC BIC logLik
2897.008 2915.691 -1443.504
Random effects:
Formula: ~1 | id
(Intercept) Residual
StdDev: 16.00934 22.44341

Fixed effects: weight ~ prog + month


Value Std.Error DF t-value p-value
(Intercept) 262.48704 3.726296 247 70.44182 0
progExercise -44.56987 4.845601 60 -9.19801 0
month -3.05774 0.301914 247 -10.12785 0
Number of Observations: 310
Number of Groups: 62
(i) Based on this output, write two explicit expressions for the average trends in
the two groups. [4]
(ii) Using your results in (a) or otherwise, write down a null hypothesis that ad-
dresses the analyst’s claim of similar slopes in time between the two groups. [2]
(d) Using relevant output, perform a formal statistical test to assess the analyst’s
claim of similar slopes in the two groups. Comment on your results. [5]

A2. Distinguish the following terms;


(a) longitudinal and cross sectional data; [2]
(b) retrospective and prospective study; [2]
(c) random efffects and fixed effects
(d) long and wide format; [2]
(e) balance and unbalanced longitudinal data. [2]

END OF ASSIGNMENT.

page 2 of 2

You might also like